# Don't Say What You Don't Know: Improving the Consistency of Abstractive Summarization by Constraining Beam Search

arXiv: https://arxiv.org/abs/2203.08436 · HTML: https://mlsanity.com/paper/2203.08436/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 47 references that are in the map.
- First posted on arXiv 16 Mar 2022.

## Builds on (most cited first, 30 of 37)

- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond](https://mlsanity.com/paper/1602.06023/) (2016)
- [SummEval: Re-evaluating Summarization Evaluation](https://mlsanity.com/paper/2007.12626/) (2020)
- [Unified Language Model Pre-training for Natural Language Understanding and Generation](https://mlsanity.com/paper/1905.03197/) (2019)
- [Evaluating the Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/1910.12840/) (2019)
- [A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents](https://mlsanity.com/paper/1804.05685/) (2018)
- [Asking and Answering Questions to Evaluate the Factual Consistency of Summaries](https://mlsanity.com/paper/2004.04228/) (2020)
- [Generating Wikipedia by Summarizing Long Sequences](https://mlsanity.com/paper/1801.10198/) (2018)
- [FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization](https://mlsanity.com/paper/2005.03754/) (2020)
- [Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics](https://mlsanity.com/paper/2104.13346/) (2021)
- [Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search](https://mlsanity.com/paper/1704.07138/) (2017)
- [BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarization](https://mlsanity.com/paper/1906.03741/) (2019)
- [Hierarchical Transformers for Multi-Document Summarization](https://mlsanity.com/paper/1905.13164/) (2019)
- [Entity-level Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/2102.09130/) (2021)
- [Optimizing the Factual Correctness of a Summary: A Study of Summarizing Radiology Reports](https://mlsanity.com/paper/1911.02541/) (2019)
- [Multi-Fact Correction in Abstractive Text Summarization](https://mlsanity.com/paper/2010.02443/) (2020)
- [What Have We Achieved on Text Summarization?](https://mlsanity.com/paper/2010.04529/) (2020)
- [Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generation](https://mlsanity.com/paper/1910.08684/) (2019)
- [Towards Faithful Neural Table-to-Text Generation with Content-Matching Constraints](https://mlsanity.com/paper/2005.00969/) (2020)
- [Understanding Neural Abstractive Summarization Models via Uncertainty](https://mlsanity.com/paper/2010.07882/) (2020)
- [Constrained Abstractive Summarization: Preserving Factual Consistency with Constrained Generation](https://mlsanity.com/paper/2010.12723/) (2020)

## Built on by (most cited first, 23 of 23)

- [Trusting Your Evidence: Hallucinate Less with Context-aware Decoding](https://mlsanity.com/paper/2305.14739/) (2023)
- [Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey](https://mlsanity.com/paper/2210.07700/) (2022)
- [ECTSum: A New Benchmark Dataset For Bullet Point Summarization of Long Earnings Call Transcripts](https://mlsanity.com/paper/2210.12467/) (2022)
- [Multi-LexSum: Real-World Summaries of Civil Rights Lawsuits at Multiple Granularities](https://mlsanity.com/paper/2206.10883/) (2022)
- [Correcting Diverse Factual Errors in Abstractive Summarization via Post-Editing and Language Model Infilling](https://mlsanity.com/paper/2210.12378/) (2022)
- [Beyond Summarization: Designing AI Support for Real-World Expository Writing Tasks](https://mlsanity.com/paper/2304.02623/) (2023)
- [Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization](https://mlsanity.com/paper/2311.09335/) (2023)
- [Cheetah: Natural Language Generation for 517 African Languages](https://mlsanity.com/paper/2401.01053/) (2024)
- [Entity-based SpanCopy for Abstractive Summarization to Improve the Factual Consistency](https://mlsanity.com/paper/2209.03479/) (2022)
- [Improved Beam Search for Hallucination Mitigation in Abstractive Summarization](https://mlsanity.com/paper/2212.02712/) (2022)
- [Expository Text Generation: Imitate, Retrieve, Paraphrase](https://mlsanity.com/paper/2305.03276/) (2023)
- [Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond](https://mlsanity.com/paper/2305.12289/) (2023)
- [Model-based Preference Optimization in Abstractive Summarization without Human Feedback](https://mlsanity.com/paper/2409.18618/) (2024)
- [A Method to Automate the Discharge Summary Hospital Course for Neurology Patients](https://mlsanity.com/paper/2305.06416/) (2023)
- [Mitigating Hallucination in Abstractive Summarization with Domain-Conditional Mutual Information](https://mlsanity.com/paper/2404.09480/) (2024)
- [Parameter Efficient Audio Captioning With Faithful Guidance Using Audio-text Shared Latent Representation](https://mlsanity.com/paper/2309.03340/) (2023)
- [Correction with Backtracking Reduces Hallucination in Summarization](https://mlsanity.com/paper/2310.16176/) (2023)
- [Medical Text Simplification: Optimizing for Readability with Unlikelihood Training and Reranked Beam Search Decoding](https://mlsanity.com/paper/2310.11191/) (2023)
- [On the Depth between Beam Search and Exhaustive Search for Text Generation](https://mlsanity.com/paper/2308.13696/) (2023)
- [On the Benefits of Fine-Grained Loss Truncation: A Case Study on Factuality in Summarization](https://mlsanity.com/paper/2403.05788/) (2024)
- [Entity-level Factual Adaptiveness of Fine-tuning based Abstractive Summarization Models](https://mlsanity.com/paper/2402.15162/) (2024)
- [Learning from Self Critique and Refinement for Faithful LLM Summarization](https://mlsanity.com/paper/2512.05387/) (2025)
- [TOPICAL: TOPIC Pages AutomagicaLly](https://mlsanity.com/paper/2405.01796/) (2024)

## Abstract (arXiv)

Abstractive summarization systems today produce fluent and relevant output, but often "hallucinate" statements not supported by the source text. We analyze the connection between hallucinations and training data, and find evidence that models hallucinate because they train on target summaries that are unsupported by the source. Based on our findings, we present PINOCCHIO, a new decoding method that improves the consistency of a transformer-based abstractive summarizer by constraining beam search to avoid hallucinations. Given the model states and outputs at a given step, PINOCCHIO detects likely model hallucinations based on various measures of attribution to the source text. PINOCCHIO backtracks to find more consistent output, and can opt to produce no summary at all when no consistent generation can be found. In experiments, we find that PINOCCHIO improves the consistency of generation (in terms of F1) by an average of~67% on two abstractive summarization datasets.